ChengRang

llama.cpp

AI Platforms Open Source

The C/C++ foundation for local inference. On Nov 13, 2026 it shipped 1.0.0 in step with the ggml tensor library, covering more than 150 architecture variants plus every mainstream speculative decoding method. From 1.0 it follows semantic versioning for the public C API: only a breaking change in the headers under include bumps the major version, and each backend compiles to a dynamic library loaded at runtime. Prebuilt artifacts cover Linux, macOS, Windows, Android and iOS, with Docker, Homebrew, conda-forge, Winget and others alongside

Local InferenceggmlSemantic VersioningCross-PlatformC/C++
Visit llama.cpp

Disclaimer: Review content represents our editorial team's views and experience, not commercial recommendation or investment advice. Product info and pricing may change; refer to official sources.

Overview

llama.cpp 1.0 is a promise rather than a performance milestone. It shipped 1.0.0 alongside the ggml tensor library on Nov 13, and what actually changed is one sentence: from now on, breaking changes will be marked by the major version.

The rule is spelled out by change type. A breaking change to the public C API under include bumps the major version. A backward-compatible feature, a backend update, new model support or an added API bumps the minor. A bug fix with no API change bumps the patch. ggml went to 1.0 the same day and follows the same scheme. The team added that as adoption grows it will be stricter about making API and ABI boundaries visible to downstream consumers.

Why that matters more than a benchmark number. For three and a half years the project stayed on 0.x or simply tracked build numbers, leaving Python, Node, Rust and Go bindings to guess compatibility from dates and build ids, with every upgrade a small gamble on whether it still compiles. Semantic versioning lets a binding pin dependencies by major version and lets applications follow releases in CI. For anyone compiling inference into their own program, that is worth more than a few percent of throughput.

The underlying capability is unchanged, merely confirmed by 1.0: support for more than 150 architecture variants plus every mainstream speculative decoding method. Each backend compiles into a dynamic library that can be loaded at runtime, which is why the same code base travels from laptops to phones to development boards.

Eight distribution channels are listed, an easy column to skip but a practical one: prebuilt artifacts for Linux, macOS, Windows, Android and iOS, plus Docker, Debian, Homebrew, conda-forge, MacPorts and XCFramework, with Winget on Windows. Hardware support comes from NVIDIA, AMD, Qualcomm, Arm, IBM and Intel, with self-hosted runners still being added.

Two things are missing and worth watching. No list of breaking changes shipped with the release, so what 1.0.0 changed against the previous build has to be read from release notes and diffs. And no roadmap appeared, with duplex or multimodal direction left unmentioned. Read 1.0 as the start of stability, not a feature boundary.

Key Features

Use Cases

Pros

Pricing

MIT licensed and free, with no royalty for commercial use or redistribution. Costs sit in your own hardware and engineering. There is no hosted offering and no paid tier.

Summary

The value is not the number 1.0 but the version semantics now available to depend on. Bindings and applications can finally judge upgrade risk by major version, which is more useful to teams embedding inference than throughput figures. Watch that no breaking-change list or feature roadmap shipped with it; 1.0 marks the start of stability, nothing more.

Version History

Category
AI Platforms
Pricing
Open Source
Tags
Local Inference · ggml · Semantic Versioning
Website

Related Tools